*   Add determinism-unimplemented exception-throwing to the following ops.
        When op-determinism is expected (i.e. after
        `tf.config.experimental.enable_op_determinism` has been called), an
        attempt to use the specified paths through the following ops on a GPU
        will cause `tf.errors.UnimplementedError` (with an understandable
        message), unless otherwise specified, to be thrown.

// x will be resized to the size of m and overwritten. // //go:norace func (x *Nat) montgomeryMul(a *Nat, b *Nat, m *Modulus) *Nat { n := len(m.nat.limbs) mLimbs := m.nat.limbs[:n] aLimbs := a.limbs[:n] bLimbs := b.limbs[:n] switch n { default: // Attempt to use a stack-allocated backing array. T := make([]uint, 0, preallocLimbs*2) if cap(T) < n*2 { T = make([]uint, 0, n*2) } T = T[:n*2] // This loop implements Word-by-Word Montgomery Multiplication, as // described in Algorithm 4 (Fig. 3) of "Efficient...

// x will be resized to the size of m and overwritten. // //go:norace func (x *Nat) montgomeryMul(a *Nat, b *Nat, m *Modulus) *Nat { n := len(m.nat.limbs) mLimbs := m.nat.limbs[:n] aLimbs := a.limbs[:n] bLimbs := b.limbs[:n] switch n { default: // Attempt to use a stack-allocated backing array. T := make([]uint, 0, preallocLimbs*2) if cap(T) < n*2 { T = make([]uint, 0, n*2) } T = T[:n*2] // This loop implements Word-by-Word Montgomery Multiplication, as // described in Algorithm 4 (Fig. 3) of "Efficient...